{"id":"https://openalex.org/W2088136809","doi":"https://doi.org/10.1109/scis-isis.2012.6505358","title":"Multi-scale Q-learning of a mobile robot in dynamic environments","display_name":"Multi-scale Q-learning of a mobile robot in dynamic environments","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2088136809","doi":"https://doi.org/10.1109/scis-isis.2012.6505358","mag":"2088136809"},"language":"en","primary_location":{"id":"doi:10.1109/scis-isis.2012.6505358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/scis-isis.2012.6505358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060731302","display_name":"Noriko Takase","orcid":null},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Noriko Takase","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan","Tokyo Metropolitan University, Tokyo/Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo/Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074076109","display_name":"Naoyuki Kubota","orcid":"https://orcid.org/0000-0001-8829-037X"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kubota","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan","Tokyo Metropolitan University, Tokyo/Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo/Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113967419","display_name":"Norio Baba","orcid":null},"institutions":[{"id":"https://openalex.org/I141479679","display_name":"Osaka Kyoiku University","ror":"https://ror.org/051j8zv27","country_code":"JP","type":"education","lineage":["https://openalex.org/I141479679"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norio Baba","raw_affiliation_strings":["Osaka Kyoiku University, Osaka, Japan","Osaka Kyoiku University,Osaka,JAPAN"],"affiliations":[{"raw_affiliation_string":"Osaka Kyoiku University, Osaka, Japan","institution_ids":["https://openalex.org/I141479679"]},{"raw_affiliation_string":"Osaka Kyoiku University,Osaka,JAPAN","institution_ids":["https://openalex.org/I141479679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060731302"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72629532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1248","last_page":"1252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8874461650848389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762108445167542},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.7034714818000793},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6456652879714966},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.643805742263794},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5294299721717834},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5124936103820801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093877911567688},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.501521110534668},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.49117085337638855},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.4314059317111969},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09284675121307373}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8874461650848389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762108445167542},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.7034714818000793},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6456652879714966},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.643805742263794},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5294299721717834},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5124936103820801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093877911567688},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.501521110534668},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.49117085337638855},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4314059317111969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09284675121307373},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/scis-isis.2012.6505358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/scis-isis.2012.6505358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1985125279","https://openalex.org/W1994955764","https://openalex.org/W2103285838","https://openalex.org/W2107726111","https://openalex.org/W2114313523","https://openalex.org/W2117195037","https://openalex.org/W2156828234","https://openalex.org/W2162219879","https://openalex.org/W2319588593","https://openalex.org/W2911283634","https://openalex.org/W3011120880","https://openalex.org/W6676697060","https://openalex.org/W6683539816"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W4400868993","https://openalex.org/W2806157618","https://openalex.org/W2532691423","https://openalex.org/W4298064558","https://openalex.org/W4237948300","https://openalex.org/W2383312578","https://openalex.org/W1987864653","https://openalex.org/W2514059013","https://openalex.org/W1522153944"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,103],"a":[4,9,20,36,66],"state-dependent":[5],"learning":[6,43,74,87],"method":[7],"of":[8,19,32,41,58,75,83,113],"mobile":[10,21],"robot":[11,22],"in":[12,29,60,90,99],"dynamic":[13,91],"and":[14,88],"unknown":[15],"environments.":[16],"The":[17],"aim":[18],"is":[23,50],"to":[24,53,70],"find":[25],"the":[26,30,55,72,81,100,111,114],"optimal":[27],"path":[28],"task":[31],"maze":[33],"navigation":[34],"on":[35],"grid":[37,101],"world.":[38],"Various":[39],"types":[40],"reinforcement":[42,76],"methods":[44],"have":[45],"been":[46],"proposed,":[47],"but":[48],"it":[49],"very":[51],"difficult":[52],"design":[54],"granularity":[56],"(resolution)":[57],"states":[59],"search":[61],"space.":[62],"Therefore,":[63],"we":[64,79,94],"propose":[65],"multi-scale":[67],"value":[68],"function":[69],"enhance":[71],"initial":[73],"learning.":[77],"First,":[78],"compare":[80],"performance":[82],"temporal":[84],"difference":[85],"(TD)":[86],"Q-learning":[89],"environment.":[92],"Here":[93],"assume":[95],"several":[96],"obstacles":[97],"disappear":[98],"world":[102],"an":[104],"existence":[105],"probability.":[106],"Several":[107],"experimental":[108],"results":[109],"show":[110],"effectiveness":[112],"proposed":[115],"method.":[116]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}